An analog VLSI massively parallel module for low-level cortical processing in machine vision

A new approach to analog VLSI implementations of algorithms for visual cortical processing is presented. Specifically, we introduce a massively parallel architecture, organized as a planar resistive network with voltage controlled current generators locally connected to model interaction schemata responsible for specific sensitivities in cortical neurons. We demonstrate the feasibility of this approach by designing and simulating 24/spl times/24 node analog modules implementing Gabor-like oriented receptive fields, that can be used in machine vision real time systems to evidence texture differences.